一种基于纹理的Mean Shift目标跟踪算法Matlab源代码,论文<Robust Object Tracking using Joint Color-Texture Histogram>发表在2009年的International Journal of Pattern Recognition and Artifical Intelligence.-Matlab Code for An Texture based Mean Shift Tracking Algroithm. The

基于纹理和边缘方向特征融合的目标跟踪程序代码，是基于mean shift框架的-This paper proposes a powerful and robust local descr iptor,called textureorientation descr iptor(TOD). TOD consists of two components: texture and orientation. Considering that the human shape shows more s

：基于背景建模的运动目标分割是智能视频监控的重要任务，模型的质量直接影响到检测、跟踪、识别等运动分析的准确性．当前的建模方法多是单层的，忽略了像素特征在时域和空域上的联系，模型描述不够准确，对于背景扰动、全局光照变化及复杂的室内外场景等多种情况鲁棒性不强，导致了分割中出现空洞和噪声点．针对这些问题提出了一种双层建模的方法，在第一层提取时域上的像素亮度特征采用码本建模，第二层提取邻域纹理特征采用基于中心对称的局部二值模式建模．实验证明该方法在用于运动分割时，比常用方法具有更好的准确性和鲁棒性．-M

This DSSIM program has been created by Philipp Klaus Krause based on Rabah Mehdi's C++ implementation of SSIM (http://mehdi.rabah.free.fr/SSIM). Originally it has been created for the VMV '09 paper "ftc - floating precision texture compressio